© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1352
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal claims and assertions of rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    hopes to, representing herself, think you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dessen
    -0.57
    νό
    -0.53
     deren
    -0.52
     '&#
    -0.45
    (&(
    -0.44
    ρο
    -0.43
     feed
    -0.42
     tín
    -0.42
    rios
    -0.41
    ca
    -0.41
    POSITIVE LOGITS
     being
    0.90
     utafitiHapana
    0.87
    自己是
    0.86
    ValueStyle
    0.82
     unknownFields
    0.81
    Being
    0.80
    being
    0.78
     Being
    0.76
     Normdatei
    0.75
     resourceCulture
    0.74
    Activations Density 0.440%

    No Known Activations